{"total":81,"rows":[{"id":"2110.13214","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","created":"2021-10-25","cited_by_count":267,"area":null},{"id":"2112.07566","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","created":"2021-12-14","cited_by_count":135,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2106.11013","title":"Interventional Video Grounding with Dual Contrastive Learning","created":"2021-06-21","cited_by_count":94,"area":null},{"id":"2303.07274","title":"Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images","created":"2023-03-13","cited_by_count":80,"area":null},{"id":"2110.01705","title":"Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning","created":"2021-10-04","cited_by_count":76,"area":null},{"id":"2106.00245","title":"Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models","created":"2021-06-01","cited_by_count":75,"area":null},{"id":"2108.10008","title":"BiaSwap: Removing dataset bias with bias-tailored swapping augmentation","created":"2021-08-23","cited_by_count":70,"area":null},{"id":"2112.01008","title":"Editing a classifier by rewriting its prediction rules","created":"2021-12-02","cited_by_count":65,"area":null},{"id":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57,"area":null},{"id":"2102.12594","title":"Directional Bias Amplification","created":"2021-02-24","cited_by_count":54,"area":null},{"id":"2203.16586","title":"Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation","created":"2022-03-30","cited_by_count":51,"area":null},{"id":"2109.04014","title":"Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering","created":"2021-09-09","cited_by_count":50,"area":null},{"id":"2402.12715","title":"The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning","created":"2024-02-20","cited_by_count":41,"area":null},{"id":"2106.02112","title":"Finding and Fixing Spurious Patterns with Explanations","created":"2021-06-03","cited_by_count":38,"area":null},{"id":"2304.03391","title":"Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval","created":"2023-04-06","cited_by_count":36,"area":null},{"id":"2207.09504","title":"Invariant Feature Learning for Generalized Long-Tailed Classification","created":"2022-07-19","cited_by_count":34,"area":null},{"id":"2302.13668","title":"Contrastive Video Question Answering via Video Graph Transformer","created":"2023-02-27","cited_by_count":32,"area":null},{"id":"2106.01127","title":"Towards Robust Classification Model by Counterfactual and Invariant Data Generation","created":"2021-06-02","cited_by_count":30,"area":null},{"id":"2307.11471","title":"Robust Visual Question Answering: Datasets, Methods, and Future Challenges","created":"2023-07-21","cited_by_count":23,"area":null},{"id":"2110.01013","title":"Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering","created":"2021-10-03","cited_by_count":22,"area":null},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"id":"2210.11924","title":"Men Also Do Laundry: Multi-Attribute Bias Amplification","created":"2022-10-21","cited_by_count":21,"area":null},{"id":"2210.10362","title":"CPL: Counterfactual Prompt Learning for Vision and Language Models","created":"2022-10-19","cited_by_count":18,"area":null},{"id":"2310.07379","title":"Causal Unsupervised Semantic Segmentation","created":"2023-10-11","cited_by_count":18,"area":null},{"id":"2305.04224","title":"Visual Causal Scene Refinement for Video Question Answering","created":"2023-05-07","cited_by_count":16,"area":null},{"id":"2106.04484","title":"Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions","created":"2021-06-08","cited_by_count":15,"area":null},{"id":"2104.00170","title":"Are Bias Mitigation Techniques for Deep Learning Effective?","created":"2021-04-01","cited_by_count":14,"area":null},{"id":"2109.06122","title":"Discovering the Unknown Knowns: Turning Implicit Knowledge in the Dataset into Explicit Training Examples for Visual Question Answering","created":"2021-09-13","cited_by_count":14,"area":null},{"id":"2211.03779","title":"CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering","created":"2022-11-07","cited_by_count":13,"area":null},{"id":"2403.01300","title":"Causal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detection","created":"2024-03-02","cited_by_count":13,"area":null},{"id":"2408.02464","title":"Fairness and Bias Mitigation in Computer Vision: A Survey","created":"2024-08-05","cited_by_count":13,"area":null},{"id":"2208.01813","title":"TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation","created":"2022-08-03","cited_by_count":12,"area":null},{"id":"2412.13989","title":"What makes a good metric? Evaluating automatic metrics for text-to-image consistency","created":"2024-12-18","cited_by_count":12,"area":null},{"id":"2502.15895","title":"Directional Gradient Projection for Robust Fine-Tuning of Foundation Models","created":"2025-02-21","cited_by_count":11,"area":null},{"id":"2103.03048","title":"Detecting Spurious Correlations with Sanity Tests for Artificial Intelligence Guided Radiology Systems","created":"2021-03-04","cited_by_count":10,"area":null},{"id":"2209.08860","title":"A Survey of Deep Causal Models and Their Industrial Applications","created":"2022-09-19","cited_by_count":10,"area":null},{"id":"2211.10370","title":"Invariant Learning via Diffusion Dreamed Distribution Shifts","created":"2022-11-18","cited_by_count":10,"area":null},{"id":"2110.07165","title":"Semantically Distributed Robust Optimization for Vision-and-Language Inference","created":"2021-10-14","cited_by_count":9,"area":null},{"id":"2411.01713","title":"Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models","created":"2024-11-03","cited_by_count":9,"area":null},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2110.11205","title":"Robustness through Data Augmentation Loss Consistency","created":"2021-10-21","cited_by_count":8,"area":null},{"id":"2111.13108","title":"Combating Unknown Bias with Effective Bias-Conflicting Scoring and Gradient Alignment","created":"2021-11-25","cited_by_count":8,"area":null},{"id":"2203.17219","title":"SimVQA: Exploring Simulated Environments for Visual Question Answering","created":"2022-03-31","cited_by_count":8,"area":null},{"id":"2305.00455","title":"Causalainer: Causal Explainer for Automatic Video Summarization","created":"2023-04-30","cited_by_count":8,"area":null},{"id":"2305.15015","title":"Measuring Faithful and Plausible Visual Grounding in VQA","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2411.11150","title":"A Comprehensive Survey on Visual Question Answering Datasets and Algorithms","created":"2024-11-17","cited_by_count":8,"area":null},{"id":"2105.04780","title":"Cross-Modal Generative Augmentation for Visual Question Answering","created":"2021-05-11","cited_by_count":7,"area":null},{"id":"2209.08799","title":"Probing Spurious Correlations in Popular Event-Based Rumor Detection Benchmarks","created":"2022-09-19","cited_by_count":7,"area":null},{"id":"2405.11685","title":"ColorFoil: Investigating Color Blindness in Large Vision and Language Models","created":"2024-05-19","cited_by_count":7,"area":null},{"id":"2311.12159","title":"Conditional Modeling Based Automatic Video Summarization","created":"2023-11-20","cited_by_count":6,"area":null},{"id":"2106.14069","title":"Saying the Unseen: Video Descriptions via Dialog Agents","created":"2021-06-26","cited_by_count":5,"area":null},{"id":"2110.06863","title":"Improving Users' Mental Model with Attention-directed Counterfactual Edits","created":"2021-10-13","cited_by_count":5,"area":null},{"id":"2203.01322","title":"Recent, rapid advancement in visual question answering architecture: a review","created":"2022-03-02","cited_by_count":5,"area":null},{"id":"2505.21755","title":"FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2311.16941","title":"Debiasing Multimodal Models via Causal Information Minimization","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2106.13445","title":"A Picture May Be Worth a Hundred Words for Visual Question Answering","created":"2021-06-25","cited_by_count":3,"area":null},{"id":"2203.15529","title":"Treatment Learning Causal Transformer for Noisy Image Classification","created":"2022-03-29","cited_by_count":3,"area":null},{"id":"2409.14637","title":"Not Only the Last-Layer Features for Spurious Correlations: All Layer Deep Feature Reweighting","created":"2024-09-23","cited_by_count":3,"area":null},{"id":"2410.10184","title":"Eliminating the Language Bias for Visual Question Answering with fine-grained Causal Intervention","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2501.07305","title":"The Devil is in the Spurious Correlations: Boosting Moment Retrieval with Dynamic Learning","created":"2025-01-13","cited_by_count":3,"area":null},{"id":"2106.08914","title":"$C^3$: Compositional Counterfactual Contrastive Learning for Video-grounded Dialogues","created":"2021-06-16","cited_by_count":2,"area":null},{"id":"2207.01772","title":"Vision-and-Language Pretraining","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2311.14837","title":"Benchmarking Robustness of Text-Image Composed Retrieval","created":"2023-11-24","cited_by_count":2,"area":null},{"id":"2401.15646","title":"Improving Data Augmentation for Robust Visual Question Answering with Effective Curriculum Learning","created":"2024-01-28","cited_by_count":2,"area":null},{"id":"2103.16795","title":"Multi-Class Multi-Instance Count Conditioned Adversarial Image Generation","created":"2021-03-31","cited_by_count":1,"area":null},{"id":"2307.10405","title":"Generative Visual Question Answering","created":"2023-07-18","cited_by_count":1,"area":null},{"id":"2508.12430","title":"Adversarial Attacks on VQA-NLE: Exposing and Alleviating Inconsistencies in Visual Question Answering Explanations","created":"2025-08-17","cited_by_count":1,"area":null},{"id":"2601.11995","title":"Learning Audio-Visual Embeddings with Inferred Latent Interaction Graphs","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2302.11414","title":"Delving into Identify-Emphasize Paradigm for Combating Unknown Bias","created":"2023-02-22","cited_by_count":0,"area":null},{"id":"2303.02601","title":"Knowledge-Based Counterfactual Queries for Visual Question Answering","created":"2023-03-05","cited_by_count":0,"area":null},{"id":"2403.14140","title":"Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2406.18901","title":"Autoencoder based approach for the mitigation of spurious correlations","created":"2024-06-27","cited_by_count":0,"area":null},{"id":"2505.20830","title":"Causality-Driven Infrared and Visible Image Fusion","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2601.04563","title":"A Vision for Multisensory Intelligence: Sensing, Science, and Synergy","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2605.07919","title":"MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.02168","title":"Disentanglement-Based Equivariant Learning for Compositional VQA","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2608.09209","title":"UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.28603","title":"C3-UniMM: Causal Cycle-Consistent Unified Multimodal Modeling via Super Alignment and Shared Decoding Space","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2609.03429","title":"When Do Frozen VLMs Respond to Image-Free Object-Token Edits? An Answer-Key-Free Protocol and What It Reveals","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.34480","title":"When Does an Image Determine the Answer? Benchmarking Visual Answerability across Charts and Scenes","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}